{"id":"https://openalex.org/W2106278012","doi":"https://doi.org/10.1109/snpd.2015.7176172","title":"Optimizing strassen matrix multiply on GPUs","display_name":"Optimizing strassen matrix multiply on GPUs","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2106278012","doi":"https://doi.org/10.1109/snpd.2015.7176172","mag":"2106278012"},"language":"en","primary_location":{"id":"doi:10.1109/snpd.2015.7176172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2015.7176172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006797454","display_name":"Ayaz H. Khan","orcid":"https://orcid.org/0000-0003-1167-7319"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]},{"id":"https://openalex.org/I4210152837","display_name":"Dhahran Health Center","ror":"https://ror.org/03pjj1n42","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I2800952698","https://openalex.org/I4210143841","https://openalex.org/I4210152837"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ayaz ul Hasan Khan","raw_affiliation_strings":["Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I4210152837"]},{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057598450","display_name":"Mayez Al-Mouhamed","orcid":"https://orcid.org/0000-0002-6309-699X"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]},{"id":"https://openalex.org/I4210152837","display_name":"Dhahran Health Center","ror":"https://ror.org/03pjj1n42","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I2800952698","https://openalex.org/I4210143841","https://openalex.org/I4210152837"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mayez Al-Mouhamed","raw_affiliation_strings":["Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I4210152837"]},{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008308549","display_name":"Allam Fatayer","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]},{"id":"https://openalex.org/I4210152837","display_name":"Dhahran Health Center","ror":"https://ror.org/03pjj1n42","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I2800952698","https://openalex.org/I4210143841","https://openalex.org/I4210152837"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Allam Fatayer","raw_affiliation_strings":["Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science & Engineering, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I4210152837"]},{"raw_affiliation_string":"Department of Computer Engineering, College of Computer Science and Engineering, KFUPM, Dhahran 31261, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/strassen-algorithm","display_name":"Strassen algorithm","score":0.9569879770278931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322614192962646},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6774832010269165},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5935947895050049},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5285502672195435},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.46841850876808167},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.4652785658836365},{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.45006975531578064},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.44467946887016296},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3570583462715149},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20217600464820862},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.12029218673706055}],"concepts":[{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.9569879770278931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322614192962646},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6774832010269165},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5935947895050049},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5285502672195435},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.46841850876808167},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.4652785658836365},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.45006975531578064},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.44467946887016296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3570583462715149},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20217600464820862},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.12029218673706055},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/snpd.2015.7176172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2015.7176172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/599106","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/599106","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W152964218","https://openalex.org/W1863336885","https://openalex.org/W1970548269","https://openalex.org/W1978171430","https://openalex.org/W1979505029","https://openalex.org/W1996487631","https://openalex.org/W2011498909","https://openalex.org/W2032839380","https://openalex.org/W2035476608","https://openalex.org/W2036668966","https://openalex.org/W2051260099","https://openalex.org/W2063186542","https://openalex.org/W2064941923","https://openalex.org/W2070966792","https://openalex.org/W2080063509","https://openalex.org/W2099021415","https://openalex.org/W2100115659","https://openalex.org/W2105097308","https://openalex.org/W2106792601","https://openalex.org/W2170716619","https://openalex.org/W2170996201","https://openalex.org/W2182472769","https://openalex.org/W2398736067","https://openalex.org/W3141650078","https://openalex.org/W4256483581"],"related_works":["https://openalex.org/W1974407206","https://openalex.org/W2004916460","https://openalex.org/W2962985479","https://openalex.org/W1523285705","https://openalex.org/W2020777648","https://openalex.org/W2772956802","https://openalex.org/W2056120647","https://openalex.org/W1829171354","https://openalex.org/W2069906535","https://openalex.org/W3006227194"],"abstract_inverted_index":{"Many":[0],"core":[1],"systems":[2],"are":[3],"basically":[4],"designed":[5],"for":[6,113,136],"applications":[7],"having":[8],"large":[9,49,114],"data":[10,50],"parallelism.":[11],"Strassen":[12,60],"Matrix":[13],"Multiply":[14],"(MM)":[15],"can":[16,143],"be":[17,144],"formulated":[18],"as":[19,111],"a":[20,26,71,130],"depth":[21],"first":[22],"(DFS)":[23],"traversal":[24],"of":[25,38,48,73,87,150],"recursion":[27,101],"tree":[28],"where":[29],"all":[30],"cores":[31],"work":[32],"in":[33],"parallel":[34],"on":[35,68],"computing":[36],"each":[37],"the":[39,46,56,137,148],"NxN":[40],"sub-matrices":[41],"that":[42],"reduces":[43],"storage":[44],"at":[45],"detriment":[47],"motion":[51],"to":[52,77,90,109,122,134,146],"gather":[53],"and":[54,61,65,85,97,118,127,152],"aggregate":[55],"results.":[57],"We":[58],"propose":[59],"Winograd":[62],"algorithms":[63],"(S-MM":[64],"W-MM)":[66],"based":[67],"three":[69],"optimizations:":[70],"set":[72],"basic":[74],"algebra":[75],"functions":[76],"reduce":[78],"overhead,":[79],"invoking":[80],"efficient":[81],"library":[82],"(CUBLAS":[83],"5.5),":[84],"parameter-tuning":[86],"parametric":[88],"kernel":[89],"improve":[91],"resource":[92],"occupancy.":[93],"On":[94],"GPUs,":[95],"W-MM":[96,128],"S-MM":[98,126],"with":[99,107],"one":[100],"level":[102],"outperform":[103],"CUBLAS":[104,151],"5.5":[105],"Library":[106],"up":[108],"twice":[110],"faster":[112],"arrays":[115],"satisfying":[116],"N>=2048":[117],"N>=3072,":[119],"respectively.":[120],"Compared":[121],"NVIDIA":[123],"SDK":[124],"library,":[125],"achieved":[129],"speedup":[131],"between":[132],"20x":[133],"80x":[135],"above":[138],"arrays.":[139],"The":[140],"proposed":[141],"approach":[142],"used":[145],"enhance":[147],"performance":[149],"MKL":[153],"libraries.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}